New statistical methods to assess the effect of time-dependent exposures in case-control studies

Contexte. Les études cas-témoins sont très fréquemment utilisées par les épidémiologistes pour évaluer l’impact de certaines expositions sur une maladie particulière. Ces expositions peuvent être représentées par plusieurs variables dépendant du temps, et de nouvelles méthodes sont nécessaires pour estimer de manière précise leurs effets. En effet, la régression logistique qui est la méthode conventionnelle pour analyser les données cas-témoins ne tient pas directement compte des changements de valeurs des covariables au cours du temps. Par opposition, les méthodes d’analyse des données de survie telles que le modèle de Cox à risques instantanés proportionnels peuvent directement incorporer des covariables dépendant du temps représentant les histoires individuelles d’exposition. Cependant, cela nécessite de manipuler les ensembles de sujets à risque avec précaution à cause du sur-échantillonnage des cas, en comparaison avec les témoins, dans les études cas-témoins. Comme montré dans une étude de simulation précédente, la définition optimale des ensembles de sujets à risque pour l’analyse des données cas-témoins reste encore à être élucidée, et à être étudiée dans le cas des variables dépendant du temps. Objectif: L’objectif général est de proposer et d’étudier de nouvelles versions du modèle de Cox pour estimer l’impact d’expositions variant dans le temps dans les études cas-témoins, et de les appliquer à des données réelles cas-témoins sur le cancer du poumon et le tabac. Méthodes. J’ai identifié de nouvelles définitions d’ensemble de sujets à risque, potentiellement optimales (le Weighted Cox model and le Simple weighted Cox model), dans lesquelles différentes pondérations ont été affectées aux cas et aux témoins, afin de refléter les proportions de cas et de non cas dans la population source. Les propriétés des estimateurs des effets d’exposition ont été étudiées par simulation. Différents aspects d’exposition ont été générés (intensité, durée, valeur cumulée d’exposition). Les données cas-témoins générées ont été ensuite analysées avec différentes versions du modèle de Cox, incluant les définitions anciennes et nouvelles des ensembles de sujets à risque, ainsi qu’avec la régression logistique conventionnelle, à des fins de comparaison. Les différents modèles de régression ont ensuite été appliqués sur des données réelles cas-témoins sur le cancer du poumon. Les estimations des effets de différentes variables de tabac, obtenues avec les différentes méthodes, ont été comparées entre elles, et comparées aux résultats des simulations. Résultats. Les résultats des simulations montrent que les estimations des nouveaux modèles de Cox pondérés proposés, surtout celles du Weighted Cox model, sont bien moins biaisées que les estimations des modèles de Cox existants qui incluent ou excluent simplement les futurs cas de chaque ensemble de sujets à risque. De plus, les estimations du Weighted Cox model étaient légèrement, mais systématiquement, moins biaisées que celles de la régression logistique. L’application aux données réelles montre de plus grandes différences entre les estimations de la régression logistique et des modèles de Cox pondérés, pour quelques variables de tabac dépendant du temps. Conclusions. Les résultats suggèrent que le nouveau modèle de Cox pondéré propose pourrait être une alternative intéressante au modèle de régression logistique, pour estimer les effets d’expositions dépendant du temps dans les études cas-témoins

A Study on the Kerridge's Inaccuracy Measure and Related Conceptss

Department of Statistics, Cochin University of Sciene ans Technology

Timing and the holding periods of institutional real estate

Literature on investors' holding periods for securities suggests that high transaction costs are associated with longer holding periods. Return volatility, by contrast, is associated with shorter holding periods. In real estate, high transaction costs and illiquidity imply longer holding periods. Research on depreciation and obsolescence suggests that there might be an optimal holding period. Sales rates and holding periods for U.K. institutional real estate are analyzed, using a proportional hazards model, over an 18-year period. The results show longer holding periods than those claimed by investors, with marked differences by type of property and over time. The results shed light on investor behavior.

Desigualdade da sobrevivência de trabalhadores de Botucatu, São Paulo, Brasil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Likelihood approximations and discrete models for tied survival data

Ties among event times are often recorded in survival studies. For example, in a two week laboratory study where event times are measured in days, ties are very likely to occur. The proportional hazards model might be used in this setting using an approximated partial likelihood function. This approximation works well when the number of ties is small. on the other hand, discrete regression models are suggested when the data are heavily tied. However, in many situations it is not clear which approach should be used in practice. In this work, empirical guidelines based on Monte Carlo simulations are provided. These recommendations are based on a measure of the amount of tied data present and the mean square error. An example illustrates the proposed criterion.

Analysis of beef cattle longitudinal data applying a nonlinear model

The objective of this work was to evaluate the Nelore beef cattle, growth curve parameters using the Von Bertalanffy function in a nested Bayesian procedure that allowed estimation of the joint posterior distribution of growth curve parameters, their (co)variance components, and the environmental and additive genetic components affecting them. A hierarchical model was applied; each individual had a growth trajectory described by the nonlinear function, and each parameter of this function was considered to be affected by genetic and environmental effects that were described by an animal model. Random samples of the posterior distributions were drawn using Gibbs sampling and Metropolis-Hastings algorithms. The data set consisted of a total of 145,961 BW recorded from 15,386 animals. Even though the curve parameters were estimated for animals with few records, given that the information from related animals and the structure of systematic effects were considered in the curve fitting, all mature BW predicted were suitable. A large additive genetic variance for mature BW was observed. The parameter a of growth curves, which represents asymptotic adult BW, could be used as a selection criterion to control increases in adult BW when selecting for growth rate. The effect of maternal environment on growth was carried through to maturity and should be considered when evaluating adult BW. Other growth curve parameters showed small additive genetic and maternal effects. Mature BW and parameter k, related to the slope of the curve, presented a large, positive genetic correlation. The results indicated that selection for growth rate would increase adult BW without substantially changing the shape of the growth curve. Selection to change the slope of the growth curve without modifying adult BW would be inefficient because their genetic correlation is large. However, adult BW could be considered in a selection index with its corresponding economic weight to improve the overall efficiency of beef cattle production.

Could albumin level explain the higher mortality in hemodialysis patients with pulmonary hypertension?

Background: The pathogenesis of pulmonary hypertension (PH) in hemodialysis is still unclear. The aim of thisstudy was to identify the risk factors associated with the presence of PH in chronic hemodialysis patients and toverify whether these factors might explain the highest mortality among them.Methods: We conducted a retrospective study of hemodialysis patients who started treatment from August 2001to October 2007 and were followed up until April 2011 in a Brazilian referral medical school. According to theresults of echocardiography examination, patients were allocated in two groups: those with PH and those withoutPH. Clinical parameters, site and type of vascular access, bioimpedance, and laboratorial findings were comparedbetween the groups and a logistic regression model was elaborated. Actuarial survival curves were constructed andhazard risk to death was evaluated by Cox regression analysis.Results: PH > 35 mmHg was found in 23 (30.6%) of the 75 patients studied. The groups differed in extracellularwater, ventricular thickness, left atrium diameter, and ventricular filling. In a univariate analysis, extracellular waterwas associated with PH (relative risk = 1.194; 95% CI of 1.006 1.416; p = 0.042); nevertheless, in a multiple model,only left atrium enlargement was independently associated with PH (relative risk =1.172; 95% CI of 1.010 1.359;p = 0.036). PH (hazard risk = 3.008; 95% CI of 1.285 7.043; p = 0.011) and age (hazard risk of 1.034 per year of age;95% CI of 1.000 7.068; p = 0.047) were significantly associated with mortality in a multiple Cox regression analysis.However, when albumin was taken in account the only statistically significant association was between albuminlevel and mortality (hazard risk = 0.342 per g/dL; 95% CI of 0.119 0.984; p = 0.047) while the presence of PH lost itsstatistical significance (p = 0.184). Mortality was higher in patients with PH (47.8% vs 25%) who also had astatistically worse survival after the sixth year of follow up.Conclusions: PH in hemodialysis patients is associated with parameters of volume overload that sheds light on itspathophysiology. Mortality is higher in hemodialysis patients with PH and the low albumin level can explain thisassociation.© 2012 Greenfield et al.; licensee BioMed Central Ltd.

Three-year follow-up of Interleukin 6 and C-reactive protein in chronic obstructive pulmonary disease

Background: Past studies have shown that mean values of Interleukin-6 (IL-6) and C-reactive protein (CRP) do not change significantly in COPD patients over a one-year period. However, longer period follow-up studies are still lacking. Thus, the aim of this study is to evaluate plasma CRP and IL-6 concentration over three years in COPD patients and to test the association between these inflammatory mediators and disease outcome markers. Methods: A cohort of 77 outpatients with stable COPD was evaluated at baseline, and 53 (mean FEV1, 56% predicted) were included in the prospective study. We evaluated Interleukin-6 (IL-6), C-reactive protein (CRP), six-minute walking distance (6MWD), and body mass index (BMI) at baseline and after three years. Plasma concentration of IL-6 was measured by high sensitivity ELISA, and CRP was obtained by high sensitivity particle-enhanced immunonephelometry. Results: IL-6 increased significantly after 3 years compared to baseline measurements [0.8 (0.5-1.3) vs 2.4 (1.3-4.4) pg/ml; p < 0.001] and was associated with worse 6MWD performance. In the Cox regression, increased IL-6 at baseline was associated with mortality [Hazard Ratio (95% CI) = 2.68 (0.13, 1.84); p = 0.02]. CRP mean values did not change [5 (1.6-7.9) vs 4.7 (1.7-10) pg/L; p = 0.84], although eleven patients (21%) presented with changes >3 mg/L in CRP after 3 years. Conclusions: The systemic inflammatory process, evaluated by IL-6, seems to be persistent, progressive and associated with mortality and worse physical performance in COPD patients. Trial registration: No.:NCT00605540. © 2013 Ferrari et al; licensee BioMed Central Ltd.

Blood transfusion in cardiac surgery is a risk factor for increased hospital length of stay in adult patients

Abstract Background Allogeneic red blood cell (RBC) transfusion has been proposed as a negative indicator of quality in cardiac surgery. Hospital length of stay (LOS) may be a surrogate of poor outcome in transfused patients. Methods Data from 502 patients included in Transfusion Requirements After Cardiac Surgery (TRACS) study were analyzed to assess the relationship between RBC transfusion and hospital LOS in patients undergoing cardiac surgery and enrolled in the TRACS study. Results According to the status of RBC transfusion, patients were categorized into the following three groups: 1) 199 patients (40%) who did not receive RBC, 2) 241 patients (48%) who received 3 RBC units or fewer (low transfusion requirement group), and 3) 62 patients (12%) who received more than 3 RBC units (high transfusion requirement group). In a multivariable Cox proportional hazards model, the following factors were predictive of a prolonged hospital length of stay: age higher than 65 years, EuroSCORE, valvular surgery, combined procedure, LVEF lower than 40% and RBC transfusion of > 3 units. Conclusion RBC transfusion is an independent risk factor for increased LOS in patients undergoing cardiac surgery. This finding highlights the adequacy of a restrictive transfusion therapy in patients undergoing cardiac surgery. Trial registration Clinicaltrials.gov identifier: http://NCT01021631.

On Causal Mediation Analysis with a Survival Outcome

Suppose that having established a marginal total effect of a point exposure on a time-to-event outcome, an investigator wishes to decompose this effect into its direct and indirect pathways, also know as natural direct and indirect effects, mediated by a variable known to occur after the exposure and prior to the outcome. This paper proposes a theory of estimation of natural direct and indirect effects in two important semiparametric models for a failure time outcome. The underlying survival model for the marginal total effect and thus for the direct and indirect effects, can either be a marginal structural Cox proportional hazards model, or a marginal structural additive hazards model. The proposed theory delivers new estimators for mediation analysis in each of these models, with appealing robustness properties. Specifically, in order to guarantee ignorability with respect to the exposure and mediator variables, the approach, which is multiply robust, allows the investigator to use several flexible working models to adjust for confounding by a large number of pre-exposure variables. Multiple robustness is appealing because it only requires a subset of working models to be correct for consistency; furthermore, the analyst need not know which subset of working models is in fact correct to report valid inferences. Finally, a novel semiparametric sensitivity analysis technique is developed for each of these models, to assess the impact on inference, of a violation of the assumption of ignorability of the mediator.

Tenofovir use is associated with a reduction in calculated glomerular filtration rates in the Swiss HIV Cohort Study

BACKGROUND: A growing number of case reports have described tenofovir (TDF)-related proximal renal tubulopathy and impaired calculated glomerular filtration rates (cGFR). We assessed TDF-associated changes in cGFR in a large observational HIV cohort. METHODS: We compared treatment-naive patients or patients with treatment interruptions > or = 12 months starting either a TDF-based combination antiretroviral therapy (cART) (n = 363) or a TDF-sparing regime (n = 715). The predefined primary endpoint was the time to a 10 ml/min reduction in cGFR, based on the Cockcroft-Gault equation, confirmed by a follow-up measurement at least 1 month later. In sensitivity analyses, secondary endpoints including calculations based on the modified diet in renal disease (MDRD) formula were considered. Endpoints were modelled using pre-specified covariates in a multiple Cox proportional hazards model. RESULTS: Two-year event-free probabilities were 0.65 (95% confidence interval [CI] 0.58-0.72) and 0.80 (95% CI 0.76-0.83) for patients starting TDF-containing or TDF-sparing cART, respectively. In the multiple Cox model, diabetes mellitus (hazard ratio [HR] = 2.34 [95% CI 1.24-4.42]), higher baseline cGFR (HR = 1.03 [95% CI 1.02-1.04] by 10 ml/min), TDF use (HR = 1.84 [95% CI 1.35-2.51]) and boosted protease inhibitor use (HR = 1.71 [95% CI 1.30-2.24]) significantly increased the risk for reaching the primary endpoint. Sensitivity analyses showed high consistency. CONCLUSION: There is consistent evidence for a significant reduction in cGFR associated with TDF use in HIV-infected patients. Our findings call for a strict monitoring of renal function in long-term TDF users with tests that distinguish between glomerular dysfunction and proximal renal tubulopathy, a known adverse effect of TDF.

Comparison of drug retention rates and causes of drug discontinuation between anti-tumor necrosis factor agents in rheumatoid arthritis

OBJECTIVE: Tumor necrosis factor (TNF) inhibitors have revolutionized the treatment of severe rheumatoid arthritis (RA), yet drug discontinuation is common. The aim of this study was to compare treatment retention rates and specific causes of anti-TNF discontinuation in a population-based RA cohort. METHODS: All patients treated with etanercept, infliximab, or adalimumab within the Swiss Clinical Quality Management RA cohort between 1997 and 2006 were included in the study. Causes of treatment discontinuation were broadly categorized as adverse events (AEs) or nontoxic causes, and further subdivided into specific categories. Specific causes of treatment interruption were analyzed using a Cox proportional hazards model and adjusted for potential confounders. RESULTS: A total of 2,364 anti-TNF treatment courses met the inclusion criteria. Treatment discontinuation was reported 803 times: 309 with etanercept, 249 with infliximab, and 245 with adalimumab. Drug inefficacy represented the largest single cause of treatment discontinuation (55.8% of cases). The median time of receiving anti-TNF therapy was 37 months, but discontinuation rates differed between the 3 anti-TNF agents (P < 0.001), with shorter retention rates for infliximab (hazard ratio [HR] 1.24, 99% confidence interval [99% CI] 1.01-1.51). The specific causes of treatment discontinuation revealed an increased risk of AEs with infliximab (HR 1.4, 99% CI 1.003-1.96), mostly due to an increased risk of infusion or allergic reactions (HR 2.11, 99% CI 1.23-3.62). Other discontinuation causes were equally distributed between the anti-TNF agents. CONCLUSION: In this population, infliximab was associated with higher overall discontinuation rates compared with etanercept and adalimumab, which is mainly due to an increased risk of infusion or allergic reactions.

The critical role and regulation of transcription factor FoxM1 in gastric cancer development and progression

The mammalian Forkhead Box (Fox) transcription factor (FoxM1) is implicated in tumorgenesis. However, the role and regulation of FoxM1 in gastric cancer remain unknown.^ I examined FoxM1 expression in 86 cases of primary gastric cancer and 57 normal gastric tissue specimens. I found weak expression of FoxM1 protein in normal gastric mucosa, whereas I observed strong staining for FoxM1 in tumor-cell nuclei in various gastric tumors and lymph node metastases. The aberrant FoxM1 expression is associated with VEGF expression and increased angiogenesis in human gastric cancer. A Cox proportional hazards model revealed that FoxM1 expression was an independent prognostic factor in multivariate analysis. Furthermore, overexpression of FoxM1 by gene transfer significantly promoted the growth and metastasis of gastric cancer cells in orthotopic mouse models, whereas knockdown of FoxM1 expression by small interfering RNA did the opposite. Next, I observed that alteration of tumor growth and metastasis by elevated FoxM1 expression was directly correlated with alteration of VEGF expression and angiogenesis. In addition, promotion of gastric tumorigenesis by FoxM1 directly and significantly correlated with transactivation of vascular endothelial growth factor (VEGF) expression and elevation of angiogenesis. ^ To further investigate the underlying mechanisms that result in FoxM1 overexpression in gastric cancer, I investigated FoxM1 and Krüppel-like factor 4 (KLF4) expressions in primary gastric cancer and normal gastric tissue specimens. Concomitance of increased expression of FoxM1 protein and decreased expression of KLF4 protein was evident in human gastric cancer. Enforced KLF4 expression suppressed FoxM1 protein expression. Moreover, a region within the proximal FoxM1 promoter was identified to have KLF4-binding sites. Finally, I found an increased FoxM1 expression in gastric mucosa of villin-Cre -directed tissue specific Klf4-null mice.^ In summary, I offered both clinical and mechanistic evidence that dysregulated expression of FoxM1 play an important role in gastric cancer development and progression, while KLF4 mediates negative regulation of FoxM1 expression and its loss significantly contributes to FoxM1 dysregulation. ^